让我们建立一个简单的数据库3

已于 2023-08-25 16:00:37 修改
阅读量81 收藏
点赞数
分类专栏： Database 文章标签： 开发语言
于 2023-08-23 09:34:11 首次发布
原文链接：https://cstack.github.io/db_tutorial/parts/part3.html
版权
本文详细描述了一个基于内存的、仅支持插入和查询的简单数据库系统，涉及数据类型处理、SQL语句解析、内存页管理及B树概念的应用。作者展示了如何在内存中存储用户数据、执行插入和选择操作，以及表的初始化和内存释放过程。
摘要由CSDN通过智能技术生成

第 3 部分 - 内存式、仅用于追加的单表数据库　　

　　我们将从小处着手，对数据库进行大量限制。目前，它将

  • 支持两种操作：插入一行和打印所有行
  • 仅存在于内存中（不能持久存在磁盘上）
  • 支持单个硬编码表

　　我们的硬编码表将存储用户，看起来像这样：

columntype
idinteger
usernamevarchar(32)
emailvarchar(255)

　　这是一个简单的模式，但它能让我们支持多种数据类型和多种大小的文本数据类型。

　　插入语句现在看起来像这样：

insert 1 cstack foo@bar.com

　　这意味着我们需要升级 prepare_statement 函数，以解析参数

   if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
     statement->type = STATEMENT_INSERT;
+    int args_assigned = sscanf(
+        input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
+        statement->row_to_insert.username, statement->row_to_insert.email);
+    if (args_assigned < 3) {
+      return PREPARE_SYNTAX_ERROR;
+    }
     return PREPARE_SUCCESS;
   }
   if (strcmp(input_buffer->buffer, "select") == 0) {

　　我们会将这些解析后的参数存储到语句对象中一个新的 Row 数据结构中：

+#define COLUMN_USERNAME_SIZE 32
+#define COLUMN_EMAIL_SIZE 255
+typedef struct {
+  uint32_t id;
+  char username[COLUMN_USERNAME_SIZE];
+  char email[COLUMN_EMAIL_SIZE];
+} Row;
+
 typedef struct {
   StatementType type;
+  Row row_to_insert;  // only used by insert statement
 } Statement;

　　现在，我们需要将这些数据复制到代表表的数据结构中。SQLite 使用 B 树来实现快速查找、插入和删除。我们将从更简单的结构开始。与 B 树一样，它也会将行分组到页面中，但不会将这些页面排列成树状，而是排列成数组。

　　我的计划是这样的

+#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)
+
+const uint32_t ID_SIZE = size_of_attribute(Row, id);
+const uint32_t USERNAME_SIZE = size_of_attribute(Row, username);
+const uint32_t EMAIL_SIZE = size_of_attribute(Row, email);
+const uint32_t ID_OFFSET = 0;
+const uint32_t USERNAME_OFFSET = ID_OFFSET + ID_SIZE;
+const uint32_t EMAIL_OFFSET = USERNAME_OFFSET + USERNAME_SIZE;
+const uint32_t ROW_SIZE = ID_SIZE + USERNAME_SIZE + EMAIL_SIZE;

　　这意味着序列化记录的布局将如下所示：

columnsize (bytes)offset
id40
username324
email25536
total291

　　我们还需要代码来转换紧凑表示法。

+void serialize_row(Row* source, void* destination) {
+  memcpy(destination + ID_OFFSET, &(source->id), ID_SIZE);
+  memcpy(destination + USERNAME_OFFSET, &(source->username), USERNAME_SIZE);
+  memcpy(destination + EMAIL_OFFSET, &(source->email), EMAIL_SIZE);
+}
+
+void deserialize_row(void* source, Row* destination) {
+  memcpy(&(destination->id), source + ID_OFFSET, ID_SIZE);
+  memcpy(&(destination->username), source + USERNAME_OFFSET, USERNAME_SIZE);
+  memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE);
+}

　　接下来是一个表结构，它指向行页并记录有多少行：

+const uint32_t PAGE_SIZE = 4096;
+#define TABLE_MAX_PAGES 100
+const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
+const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;
+
+typedef struct {
+  uint32_t num_rows;
+  void* pages[TABLE_MAX_PAGES];
+} Table;

　　我将页面大小设为 4 千字节，因为它与大多数计算机体系结构的虚拟内存系统中使用的页面大小相同。这意味着我们数据库中的一个页面对应于操作系统使用的一个页面。操作系统会将页面作为一个整体移入和移出内存，而不是将它们分割开来。

　　我任意设定了 100 页的分配上限。改用树形结构后，数据库的最大容量将只受文件最大容量的限制。(尽管我们仍将限制内存中同时保留的页面数量）

行不应跨越页面边界。由于内存中的页面可能不会彼此相邻，因此这种假设会让读/写行变得更容易。

　　说到这一点，下面就是我们如何确定特定行在内存中的读/写位置：

+void* row_slot(Table* table, uint32_t row_num) {
+  uint32_t page_num = row_num / ROWS_PER_PAGE;
+  void* page = table->pages[page_num];
+  if (page == NULL) {
+    // Allocate memory only when we try to access page
+    page = table->pages[page_num] = malloc(PAGE_SIZE);
+  }
+  uint32_t row_offset = row_num % ROWS_PER_PAGE;
+  uint32_t byte_offset = row_offset * ROW_SIZE;
+  return page + byte_offset;
+}

　　现在，我们可以让 execute_statement 读/写我们的表结构了：

-void execute_statement(Statement* statement) {
+ExecuteResult execute_insert(Statement* statement, Table* table) {
+  if (table->num_rows >= TABLE_MAX_ROWS) {
+    return EXECUTE_TABLE_FULL;
+  }
+
+  Row* row_to_insert = &(statement->row_to_insert);
+
+  serialize_row(row_to_insert, row_slot(table, table->num_rows));
+  table->num_rows += 1;
+
+  return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_select(Statement* statement, Table* table) {
+  Row row;
+  for (uint32_t i = 0; i < table->num_rows; i++) {
+    deserialize_row(row_slot(table, i), &row);
+    print_row(&row);
+  }
+  return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_statement(Statement* statement, Table* table) {
   switch (statement->type) {
     case (STATEMENT_INSERT):
-      printf("This is where we would do an insert.\n");
-      break;
+      return execute_insert(statement, table);
     case (STATEMENT_SELECT):
-      printf("This is where we would do a select.\n");
-      break;
+      return execute_select(statement, table);
   }
 }

　　最后，我们需要初始化表格，创建相应的内存释放函数，并处理一些更多的错误案例：

+ Table* new_table() {
+  Table* table = (Table*)malloc(sizeof(Table));
+  table->num_rows = 0;
+  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+     table->pages[i] = NULL;
+  }
+  return table;
+}
+
+void free_table(Table* table) {
+    for (int i = 0; table->pages[i]; i++) {
+	free(table->pages[i]);
+    }
+    free(table);
+}
 int main(int argc, char* argv[]) {
+  Table* table = new_table();
   InputBuffer* input_buffer = new_input_buffer();
   while (true) {
     print_prompt();
@@ -105,13 +203,22 @@ int main(int argc, char* argv[]) {
     switch (prepare_statement(input_buffer, &statement)) {
       case (PREPARE_SUCCESS):
         break;
+      case (PREPARE_SYNTAX_ERROR):
+        printf("Syntax error. Could not parse statement.\n");
+        continue;
       case (PREPARE_UNRECOGNIZED_STATEMENT):
         printf("Unrecognized keyword at start of '%s'.\n",
                input_buffer->buffer);
         continue;
     }

-    execute_statement(&statement);
-    printf("Executed.\n");
+    switch (execute_statement(&statement, table)) {
+      case (EXECUTE_SUCCESS):
+        printf("Executed.\n");
+        break;
+      case (EXECUTE_TABLE_FULL):
+        printf("Error: Table full.\n");
+        break;
+    }
   }
 }

　　有了这些更改，我们就可以在数据库中保存数据了！

~ ./db
db > insert 1 cstack foo@bar.com
Executed.
db > insert 2 bob bob@example.com
Executed.
db > select
(1, cstack, foo@bar.com)
(2, bob, bob@example.com)
Executed.
db > insert foo bar 1
Syntax error. Could not parse statement.
db > .exit
~

　　出于几个原因，现在是编写测试的大好时机：

  • 我们正计划大幅更改存储表的数据结构，而测试可以捕捉到回归。
  • 有一些边缘情况我们还没有手动测试过（例如，将表填满）。

　　我们将在下一部分解决这些问题。现在，这里是本部分的完整差异：

@@ -2,6 +2,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdint.h>

 typedef struct {
   char* buffer;
@@ -10,6 +11,105 @@ typedef struct {
 } InputBuffer;

+typedef enum { EXECUTE_SUCCESS, EXECUTE_TABLE_FULL } ExecuteResult;
+
+typedef enum {
+  META_COMMAND_SUCCESS,
+  META_COMMAND_UNRECOGNIZED_COMMAND
+} MetaCommandResult;
+
+typedef enum {
+  PREPARE_SUCCESS,
+  PREPARE_SYNTAX_ERROR,
+  PREPARE_UNRECOGNIZED_STATEMENT
+ } PrepareResult;
+
+typedef enum { STATEMENT_INSERT, STATEMENT_SELECT } StatementType;
+
+#define COLUMN_USERNAME_SIZE 32
+#define COLUMN_EMAIL_SIZE 255
+typedef struct {
+  uint32_t id;
+  char username[COLUMN_USERNAME_SIZE];
+  char email[COLUMN_EMAIL_SIZE];
+} Row;
+
+typedef struct {
+  StatementType type;
+  Row row_to_insert; //only used by insert statement
+} Statement;
+
+#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)
+
+const uint32_t ID_SIZE = size_of_attribute(Row, id);
+const uint32_t USERNAME_SIZE = size_of_attribute(Row, username);
+const uint32_t EMAIL_SIZE = size_of_attribute(Row, email);
+const uint32_t ID_OFFSET = 0;
+const uint32_t USERNAME_OFFSET = ID_OFFSET + ID_SIZE;
+const uint32_t EMAIL_OFFSET = USERNAME_OFFSET + USERNAME_SIZE;
+const uint32_t ROW_SIZE = ID_SIZE + USERNAME_SIZE + EMAIL_SIZE;
+
+const uint32_t PAGE_SIZE = 4096;
+#define TABLE_MAX_PAGES 100
+const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
+const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;
+
+typedef struct {
+  uint32_t num_rows;
+  void* pages[TABLE_MAX_PAGES];
+} Table;
+
+void print_row(Row* row) {
+  printf("(%d, %s, %s)\n", row->id, row->username, row->email);
+}
+
+void serialize_row(Row* source, void* destination) {
+  memcpy(destination + ID_OFFSET, &(source->id), ID_SIZE);
+  memcpy(destination + USERNAME_OFFSET, &(source->username), USERNAME_SIZE);
+  memcpy(destination + EMAIL_OFFSET, &(source->email), EMAIL_SIZE);
+}
+
+void deserialize_row(void *source, Row* destination) {
+  memcpy(&(destination->id), source + ID_OFFSET, ID_SIZE);
+  memcpy(&(destination->username), source + USERNAME_OFFSET, USERNAME_SIZE);
+  memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE);
+}
+
+void* row_slot(Table* table, uint32_t row_num) {
+  uint32_t page_num = row_num / ROWS_PER_PAGE;
+  void *page = table->pages[page_num];
+  if (page == NULL) {
+     // Allocate memory only when we try to access page
+     page = table->pages[page_num] = malloc(PAGE_SIZE);
+  }
+  uint32_t row_offset = row_num % ROWS_PER_PAGE;
+  uint32_t byte_offset = row_offset * ROW_SIZE;
+  return page + byte_offset;
+}
+
+Table* new_table() {
+  Table* table = (Table*)malloc(sizeof(Table));
+  table->num_rows = 0;
+  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+     table->pages[i] = NULL;
+  }
+  return table;
+}
+
+void free_table(Table* table) {
+  for (int i = 0; table->pages[i]; i++) {
+     free(table->pages[i]);
+  }
+  free(table);
+}
+
 InputBuffer* new_input_buffer() {
   InputBuffer* input_buffer = (InputBuffer*)malloc(sizeof(InputBuffer));
   input_buffer->buffer = NULL;
@@ -40,17 +140,105 @@ void close_input_buffer(InputBuffer* input_buffer) {
     free(input_buffer);
 }

+MetaCommandResult do_meta_command(InputBuffer* input_buffer, Table *table) {
+  if (strcmp(input_buffer->buffer, ".exit") == 0) {
+    close_input_buffer(input_buffer);
+    free_table(table);
+    exit(EXIT_SUCCESS);
+  } else {
+    return META_COMMAND_UNRECOGNIZED_COMMAND;
+  }
+}
+
+PrepareResult prepare_statement(InputBuffer* input_buffer,
+                                Statement* statement) {
+  if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
+    statement->type = STATEMENT_INSERT;
+    int args_assigned = sscanf(
+	input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
+	statement->row_to_insert.username, statement->row_to_insert.email
+	);
+    if (args_assigned < 3) {
+	return PREPARE_SYNTAX_ERROR;
+    }
+    return PREPARE_SUCCESS;
+  }
+  if (strcmp(input_buffer->buffer, "select") == 0) {
+    statement->type = STATEMENT_SELECT;
+    return PREPARE_SUCCESS;
+  }
+
+  return PREPARE_UNRECOGNIZED_STATEMENT;
+}
+
+ExecuteResult execute_insert(Statement* statement, Table* table) {
+  if (table->num_rows >= TABLE_MAX_ROWS) {
+     return EXECUTE_TABLE_FULL;
+  }
+
+  Row* row_to_insert = &(statement->row_to_insert);
+
+  serialize_row(row_to_insert, row_slot(table, table->num_rows));
+  table->num_rows += 1;
+
+  return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_select(Statement* statement, Table* table) {
+  Row row;
+  for (uint32_t i = 0; i < table->num_rows; i++) {
+     deserialize_row(row_slot(table, i), &row);
+     print_row(&row);
+  }
+  return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_statement(Statement* statement, Table *table) {
+  switch (statement->type) {
+    case (STATEMENT_INSERT):
+       	return execute_insert(statement, table);
+    case (STATEMENT_SELECT):
+	return execute_select(statement, table);
+  }
+}
+
 int main(int argc, char* argv[]) {
+  Table* table = new_table();
   InputBuffer* input_buffer = new_input_buffer();
   while (true) {
     print_prompt();
     read_input(input_buffer);

-    if (strcmp(input_buffer->buffer, ".exit") == 0) {
-      close_input_buffer(input_buffer);
-      exit(EXIT_SUCCESS);
-    } else {
-      printf("Unrecognized command '%s'.\n", input_buffer->buffer);
+    if (input_buffer->buffer[0] == '.') {
+      switch (do_meta_command(input_buffer, table)) {
+        case (META_COMMAND_SUCCESS):
+          continue;
+        case (META_COMMAND_UNRECOGNIZED_COMMAND):
+          printf("Unrecognized command '%s'\n", input_buffer->buffer);
+          continue;
+      }
+    }
+
+    Statement statement;
+    switch (prepare_statement(input_buffer, &statement)) {
+      case (PREPARE_SUCCESS):
+        break;
+      case (PREPARE_SYNTAX_ERROR):
+	printf("Syntax error. Could not parse statement.\n");
+	continue;
+      case (PREPARE_UNRECOGNIZED_STATEMENT):
+        printf("Unrecognized keyword at start of '%s'.\n",
+               input_buffer->buffer);
+        continue;
+    }
+
+    switch (execute_statement(&statement, table)) {
+	case (EXECUTE_SUCCESS):
+	    printf("Executed.\n");
+	    break;
+	case (EXECUTE_TABLE_FULL):
+	    printf("Error: Table full.\n");
+	    break;
     }
   }
 }

songgz
关注
专栏目录
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值